Titel:
Neural Network-Based Processing of Light-Fields ; Neuronale Netzwerke für die Verarbeitung von Lichtfeldern
Beteiligte:
Gul, Muhammad Shahzeb Khan
[VerfasserIn]
Erschienen:
OPUS FAU - Online publication system of Friedrich-Alexander-Universität Erlangen-Nürnberg, 2023
Sprache:
Englisch
Entstehung:
Anmerkungen:
Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
Beschreibung:
In the pursuit of acquiring an immersive visual experience, camera technology has gone through a long evolution process. Modern digital cameras can capture high-resolution high dynamic range images with an extended depth of field. However, capturing just the 2D spatial information of the visual scene is not enough to deceive human perception for an immersive experience. Alternatively, light-field imaging technology allows for capturing the directional information of light rays together on top of the conventional 2D spatial data. This additional angular information in light-field images plays a pivotal role in many applications, including post-capture refocusing, depth estimation, 3D reconstruction, and novel view rendering. The thesis reviews the complete light-field processing pipeline which includes data capturing, depth estimation, and novel view synthesis. Moreover, inspired by the success of deep learning in different computer vision applications, this dissertation proposes to solve multiple issues concerning light-field processing with the help of neural networks. Starting with the data capturing, the first highresolution high dynamic range light-field dataset is captured for the community to develop and test their algorithms. Additionally, an initial study explains the effect of tone-mapping on view rendering quality. Quantitative and qualitative analysis indicates that tone-mapping after view rendering yields better results than applying it before rendering, especially in the presence of non-Lambertian objects. Moreover, disparity estimation is more reliable and accurate from raw HDR light-field than the tonemapped light-field. Apart from HDR light fields, the thesis also presents a recurrent neural network predicting wrong disparity assignments due to the ill-posed nature of the problem. The proposed algorithm estimates a confidence value for each pixel location, filtering out the disparity outliers. The confidence for a given pixel is calculated only from its associated matching costs, without taking ...